Q-Pensieve: Boosting Sample Efficiency of Multi-Objective RL Through Memory Sharing of Q-Snapshots

TL;DR

Q-Pensieve is a novel multi-objective reinforcement learning method that enhances sample efficiency by sharing knowledge through stored Q-snapshots, outperforming existing methods on benchmark tasks.

Contribution

It introduces a Q-snapshot memory sharing approach integrated with soft policy iteration, improving sample efficiency in MORL.

Findings

Outperforms benchmark MORL methods with fewer samples

Demonstrates effective policy improvement via Q-snapshots

Provides convergence guarantees for the proposed method

Abstract

Many real-world continuous control problems are in the dilemma of weighing the pros and cons, multi-objective reinforcement learning (MORL) serves as a generic framework of learning control policies for different preferences over objectives. However, the existing MORL methods either rely on multiple passes of explicit search for finding the Pareto front and therefore are not sample-efficient, or utilizes a shared policy network for coarse knowledge sharing among policies. To boost the sample efficiency of MORL, we propose Q-Pensieve, a policy improvement scheme that stores a collection of Q-snapshots to jointly determine the policy update direction and thereby enables data sharing at the policy level. We show that Q-Pensieve can be naturally integrated with soft policy iteration with convergence guarantee. To substantiate this concept, we propose the technique of Q replay buffer, which stores the learned Q-networks from the past iterations, and arrive at a practical actor-critic implementation. Through extensive experiments and an ablation study, we demonstrate that with much fewer samples, the proposed algorithm can outperform the benchmark MORL methods on a variety of MORL benchmark tasks.